This paper proposes a load monitoring algorithm that exploits the observed time frequency characteristics of a laboratory pulsed load current and uses it to detect events and characterize them into desirable transitions or faults. An electromagnetic gun is assembled at a low voltage lab setup to provide multiple iterations of pulsed load events with a few instances of faults. Detailed analysis of the load profile is followed by a simulation using measured data to demonstrate the effectiveness of the Short Time Fourier Transform based algorithm to identify key events in the current profile and detect faults.
STFT-Based Event Detection and Classification for a DC Pulsed Load
2019-08-01
2897953 byte
Conference paper
Electronic Resource
English
A Novel Classification Method for Flutter Signals Based on the CNN and STFT
DOAJ | 2019
|The STFT-Based Estimator of Micro-Doppler Parameters
IEEE | 2017
|